Very fair observation; my take is that a relevant continuation is occurring under OpenAI Alignment Science, but I would be interested in counterpoints—the main claim I am gesturing towards here is that the agenda is alive in other parts of the community, despite the previous flagship (and the specific team) going down.
And thanks very much to you and collaborators for this update; I’ve pointed a number of people to the previous version, but with the field evolving so quickly, having a new version seems quite high-value.
Very fair observation; my take is that a relevant continuation is occurring under OpenAI Alignment Science, but I would be interested in counterpoints—the main claim I am gesturing towards here is that the agenda is alive in other parts of the community, despite the previous flagship (and the specific team) going down.
Oh, fair enough. Yeah, definitely that agenda is still very much alive! Never mind, then, carry on :)
And thanks very much to you and collaborators for this update; I’ve pointed a number of people to the previous version, but with the field evolving so quickly, having a new version seems quite high-value.